{"id":"https://openalex.org/W7166504009","doi":"https://doi.org/10.48550/arxiv.2606.27504","title":"ReWorld: Learning Better Representations for World Action Models","display_name":"ReWorld: Learning Better Representations for World Action Models","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166504009","doi":"https://doi.org/10.48550/arxiv.2606.27504"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.27504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27504","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.27504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121670047","display_name":"Tianze Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Tianze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139628375","display_name":"Lijun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Lijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139596027","display_name":"Kaixin Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Kaixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139551821","display_name":"Jingfeng Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jingfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139551642","display_name":"Yu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003248892","display_name":"Z G Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139629321","display_name":"Bing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139578245","display_name":"Guang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Guang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139581270","display_name":"Hangjun Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Hangjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139609660","display_name":"Wenyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139567129","display_name":"Haiyang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Haiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139630813","display_name":"Xinggang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinggang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.19539999961853027,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.19539999961853027,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.19359999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10610000044107437,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6560999751091003},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6402000188827515},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.541700005531311},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5182999968528748},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.444599986076355},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.40639999508857727},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3995000123977661},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39169999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690999865531921},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6560999751091003},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.598800003528595},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.31299999356269836},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.27504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27504","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.27504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27504","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5792884826660156,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"World":[0],"Action":[1,132],"Models":[2],"(WAMs)":[3],"model":[4,24],"future":[5],"environment":[6],"evolution":[7],"under":[8],"action":[9,58],"conditioning,":[10],"offering":[11],"a":[12,29],"scalable":[13],"paradigm":[14],"for":[15,37,55,120,135],"autonomous":[16],"driving.":[17],"However,":[18],"existing":[19,170],"approaches":[20],"focus":[21],"largely":[22],"on":[23,126,186,190],"architecture":[25],"design,":[26],"and":[27,72,179,192,223],"how":[28],"WAM":[30],"can":[31],"efficiently":[32],"learn":[33],"better":[34],"world":[35,57,81,147,177],"representations":[36,78,103,142],"planning":[38,73],"remains":[39],"underexplored.":[40],"To":[41],"address":[42],"this":[43,187],"gap,":[44],"we":[45,122,137,164],"propose":[46],"ReWorld,":[47],"the":[48,66,70,76,116,131,145,167],"first":[49,138],"representation":[50,171],"learning":[51,172],"framework":[52],"specifically":[53],"designed":[54],"autonomous-driving":[56],"models.":[59],"In":[60,162],"WAMs,":[61],"standard":[62],"training":[63],"supervises":[64],"only":[65,86],"output":[67],"ends":[68],"of":[69,90,97,107,169],"generation":[71,176,200],"modules,":[74],"leaving":[75],"intermediate":[77,102,128,141],"that":[79,195],"carry":[80],"knowledge":[82],"to":[83,100,153,206,213],"be":[84,154],"shaped":[85],"indirectly,":[87],"as":[88,104,219],"byproducts":[89],"fitting":[91],"these":[92],"outputs.":[93],"The":[94],"core":[95],"idea":[96],"ReWorld":[98,196],"is":[99,184],"treat":[101],"direct":[105],"targets":[106],"optimization,":[108],"shaping":[109],"them":[110,152],"along":[111],"three":[112],"complementary":[113],"dimensions.":[114],"On":[115,130],"Video":[117],"DiT":[118,133],"responsible":[119,134],"generation,":[121],"impose":[123],"future-predictive":[124],"supervision":[125],"its":[127,140],"representations.":[129],"planning,":[136],"align":[139],"cross-modally":[143],"with":[144],"video":[146,175,199],"representation,":[148],"then":[149],"further":[150],"shape":[151],"discriminative":[155],"around":[156],"safety-critical":[157],"boundaries":[158],"via":[159],"hard-negative":[160],"supervision.":[161],"addition,":[163],"systematically":[165],"analyze":[166],"effectiveness":[168],"methods":[173],"in":[174,203],"models,":[178],"discuss":[180],"why":[181],"their":[182],"performance":[183],"limited":[185],"task.":[188],"Experiments":[189],"nuScenes":[191],"NAVSIM":[193],"show":[194],"improves":[197],"fine-tuned":[198],"by":[201,227],"23.9%":[202],"FVD":[204],"(81.3":[205],"61.9),":[207],"raises":[208],"closed-loop":[209],"PDMS":[210],"from":[211],"89.1":[212],"90.4":[214],"without":[215],"any":[216],"post-training":[217],"such":[218],"RL":[220],"or":[221],"post-processing,":[222],"accelerates":[224],"from-scratch":[225],"convergence":[226],"approximately":[228],"2x.":[229]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-30T00:00:00"}